Zobrazeno 1 - 10
of 501
pro vyhledávání: '"O'Regan, J."'
Publikováno v:
In Journal of Dairy Science December 2023 106(12):8357-8367
Humans are extremely swift learners. We are able to grasp highly abstract notions, whether they come from art perception or pure mathematics. Current machine learning techniques demonstrate astonishing results in extracting patterns in information. Y
Externí odkaz:
http://arxiv.org/abs/1907.12430
Although deep neural networks (DNNs) have demonstrated impressive results during the last decade, they remain highly specialized tools, which are trained -- often from scratch -- to solve each particular task. The human brain, in contrast, significan
Externí odkaz:
http://arxiv.org/abs/1908.08017
Autor:
Laflaquière, Alban, O'Regan, J. Kevin, Argentieri, Sylvain, Gas, Bruno, Terekhov, Alexander V.
Publikováno v:
Robotics and Autonomous Systems, Volume 71, September 2015, Pages 49-59
The design of robotic systems is largely dictated by our purely human intuition about how we perceive the world. This intuition has been proven incorrect with regard to a number of critical issues, such as visual change blindness. In order to develop
Externí odkaz:
http://arxiv.org/abs/1810.01872
Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position. This paper proposes a method to estimate a certai
Externí odkaz:
http://arxiv.org/abs/1810.01866
In line with the sensorimotor contingency theory, we investigate the problem of the perception of space from a fundamental sensorimotor perspective. Despite its pervasive nature in our perception of the world, the origin of the concept of space remai
Externí odkaz:
http://arxiv.org/abs/1806.02739
Autor:
Rizza, Aurora, Terekhov, Alexander V., Montone, Guglielmo, Belardinelli, Marta Olivetti, O'Regan, J. Kevin
Tactile speech aids, though extensively studied in the 1980s and 90s, never became a commercial success. A hypothesis to explain this failure might be that it is difficult to obtain true perceptual integration of a tactile signal with information fro
Externí odkaz:
http://arxiv.org/abs/1712.04987
In the present work we propose a Deep Feed Forward network architecture which can be trained according to a sequential learning paradigm, where tasks of increasing difficulty are learned sequentially, yet avoiding catastrophic forgetting. The propose
Externí odkaz:
http://arxiv.org/abs/1711.10204
In this work we propose a system for visual question answering. Our architecture is composed of two parts, the first part creates the logical knowledge base given the image. The second part evaluates questions against the knowledge base. Differently
Externí odkaz:
http://arxiv.org/abs/1711.10185